提出立体图像超分新基准，解决视角一致性难题。
NTIRE 2024 Challenge on Stereo Image Super-Resolution: Methods and Results
- 利用双视角信息提升超分质量，保持立体一致性。
- 实测14支团队超越基线，最高PSNR达37.26（RGB）。
- 适用于计算机视觉、自动驾驶中的立体图像增强。
本文总结了第三届NTIRE立体图像超分辨率挑战赛的方法与成果。任务要求在计算资源受限条件下，将低分辨率立体图像对以4倍放大率重建为高分辨率图像。相比单图超分，主要挑战在于如何有效利用另一视点的额外信息，并保持结果的立体一致性。挑战分为两个赛道：一个针对双三次退化，另一个针对真实退化。共注册108支和70支队伍。测试阶段，分别有14支和13支队伍提交有效结果，其RGB PSNR均高于基线。本挑战建立了新的立体图像超分基准。
原文摘要 · Abstract (English)
This paper summarizes the 3rd NTIRE challenge on stereo image super-resolution (SR) with a focus on new solutions and results. The task of this challenge is to super-resolve a low-resolution stereo image pair to a high-resolution one with a magnification factor of x4 under a limited computational budget. Compared with single image SR, the major challenge of this challenge lies in how to exploit additional information in another viewpoint and how to maintain stereo consistency in the results. This challenge has 2 tracks, including one track on bicubic degradation and one track on real degradations. In total, 108 and 70 participants were successfully registered for each track, respectively. In the test phase, 14 and 13 teams successfully submitted valid results with PSNR (RGB) scores better than the baseline. This challenge establishes a new benchmark for stereo image SR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。